arXiv cs.AI· Tung-Wei Lin, Gabe Fierro, Han Li, Tianzhen Hong, Pierluigi Nuzzo, Alberto Sangiovanni-Vinentelli·· 4 小时前AI 评分26
面向多违规知识图谱修复的选择性检索路由框架
Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair
AI 导读
一篇 arXiv 论文提出知识图谱迭代修复的选择性检索框架：LLM 修复智能体负责探索和编辑图谱，路由器控制其对检索外部证据的 researcher agent 的访问，并利用违规注入生成的多违规案例训练部署专用路由器。在两个楼宇自动化数据集的六个评测套件中，路由器在所有套件中修复时 token 消耗均低于始终开启检索，在五个套件中的修复 F1 高于始终关闭检索。
正文 · 原文
Abstract:Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph. External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful. We propose a framework for selective retrieval in iterative graph repair. An LLM repair agent explores and edits the graph, while a router controls its access to a researcher agent that retrieves external evidence. We extend a violation-injection framework to generate cases with multiple compatible violations and known reference repairs. The agent's repair outcomes on these cases provide supervision for training the deployment-specific router. On two building-automation datasets, researcher access improves repairs for some violations and degrades them for others, with effects differing across deployments. The router uses fewer repair-time tokens than always enabling access in all six evaluation suites. It achieves higher repair $F_1$ than always disabling access in five of six suites.
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.07342 [cs.DB] |
| (or arXiv:2611.07342v1 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2611.07342 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tung-Wei Lin [view email]
[v1]
Thu, 5 Nov 2026 02:29:58 UTC (893 KB)
来源：arXiv cs.AI · arxiv.org